AffineQuant: Affine Transformation Quantization for Large Language Models Paper • 2403.12544 • Published Mar 19
ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models Paper • 2403.02084 • Published Mar 4 • 14
PAMS: Quantized Super-Resolution via Parameterized Max Scale Paper • 2011.04212 • Published Nov 9, 2020
Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios Paper • 2207.05501 • Published Jul 12, 2022 • 1
AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration Paper • 2309.10438 • Published Sep 19, 2023
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective Paper • 2303.11906 • Published Mar 21, 2023
SliceGPT: Compress Large Language Models by Deleting Rows and Columns Paper • 2401.15024 • Published Jan 26 • 69